Multilayer Kohonen network and its separability analysis
Chao-yuan Liu, Jie-Gu Li · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1995
This paper presents a model of a multilayer Kohonen network. Because of obeying the winner- take-all learning rule and projecting high dimensional patterns into one or two dimensional space, the conventional Kohonen network has many limitations in its applications, such as pattern separability limitation and open ended limitation. Taking advantage of the innovation for learning method and its multilayer structure, the multilayer Kohonen network has the performance of nonlinear pattern partition. Owing to labeling pattern clusters with appropriate category names or numbers only, the network is an open ended system, so it is far more powerful than the conventional Kohonen network. The mechanism of the multilayer Kohonen network is explained in detail, and its nonlinear pattern separability is analyzed theoretically. As a result of an experiment made by two layer Kohonen network, a set of human head contour figures assigned into diverse by categories is shown.